Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    select, thorough instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ♲
    0.47
    gtk
    0.46
    ソフトウェア
    0.46
     programma
    0.45
    程序
    0.45
     tunt
    0.45
     程序
    0.45
     aceptar
    0.44
    软件
    0.44
     stupidity
    0.44
    POSITIVE LOGITS
     admins
    0.63
    Admin
    0.56
    Draft
    0.54
     Admin
    0.54
     Shopify
    0.52
     impacted
    0.51
     ADMIN
    0.51
     Salesforce
    0.51
     HubSpot
    0.51
     toggle
    0.50
    Act Density 0.037%

    No Known Activations